© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48406
    Prev
    Next
    INDEX
    Explanations

    The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PTY
    -0.08
     firefight
    -0.08
    ick
    -0.07
     citizenship
    -0.07
     teamwork
    -0.07
     decl
    -0.07
    gy
    -0.07
    occo
    -0.06
     team
    -0.06
     intellig
    -0.06
    POSITIVE LOGITS
     term
    0.34
     Term
    0.23
    Term
    0.22
    term
    0.21
    _term
    0.20
     word
    0.20
     concept
    0.18
    oret
    0.18
     TERM
    0.18
    -term
    0.18
    Activations Density 0.330%

    No Known Activations